Cartoon Spider Walking a Dog in the Rain and Other AI Generated Images

[berkeman]

The online AI tools I have tried are no match for the "real" stuff, so I asked one of my friends who has got AI software if he would like to try rendering some space related images.

Great pictures! Impressive! Wondering, is there a way to set prompts in such a way as to get a "real photo effect". For example, so that in the airless space on other planets there were no pictures with an open spacesuit. Have there been any attempts to make it happen?

Thanks :)

( I made the shots above )

Welcome to PF! So you made the images that @DennisN posted? Very impressive. Can you say more about what tools you used to generate them?

 

[pxl]

Thanks nice to be here :)

Sure - happy to help out !!

You need a web UI for StableDiffusion, a few special models and perhaps a Lora or two.

You can run this locally ( if you got the hardware that can deal with the compute ) or you can hire compute in the cloud with places like runpod.io... ( links below )

..here's what you need... ( in the order you likely will need it )

Web UI
https://github.com/AUTOMATIC1111/stable-diffusion-webui

Tutorial to install on MAC...


..and on Windows


Then find models on huggingface or here ( beware...a lot of NSFW...just human nature ) on each image in the gallery you can see exactly what prompt and settings that where used...you can copy them, paste in the first field and then click the arrow and it will fill in all the fields...there's a lot of cool images here and you can turn off the NSFW in settings...highly recommended site...all the latest stuff you find here https://civitai.com/

For the ultra realistic stuff - the images I posted here - I used...
https://civitai.com/models/4201/realistic-vision-v20

How to get super high resolution...


You can accelerate this in the cloud ( 50cent-ish an hour ) with runpod...

Cloud rentals...
https://www.runpod.io/

Tutorial to do this...


I highly encourage to check out these excellent youtubers...they taught me all I know...

In particular...
https://www.youtube.com/@sebastiankamph/videos

..and also...
https://www.youtube.com/@Aitrepreneur/videos
https://www.youtube.com/@SECourses/videos

Good luck :)

//O.

 

[pxl]

Two new shots...you can see the quality is getting better by the week :)

 

[berkeman]

Wow!

 

[DennisN]

Two new shots...you can see the quality is getting better by the week :)

If I understood correctly you can train the software for particular tasks by using other images, or?
For instance, if you would like a more realistic lighthouse you could feed the software with photos of lighthouses?

Well, I've got a bunch of such photos in hi-res, so let me know if you need them .

 

[pxl]

Very kind - thank you !!

I haven't yet trained on photos aside from training a "lora" on my own face just to learn...and from that I realised I need to learn a lot more before I train full models. ( a Lora is a small network trained on a specific subject usually 10 or 15 images that can then be used in combination with a larger model trained on tens of thousands of annotated images ) But you're correct, you could make a Lora using shots of a specific subject like a lighthouse, then remix the look and use of that by combining it with a larger model...that would add a beach and ocean, change the colour and design etc.

I made a few half decent shots of characters that look like me ( easiest way to get a photograph of myself in a suit haha ) but it was overcooked or I did something wrong somewhere and that makes it hard to work with I.E I have a lot more to learn.

There's a strong community that train on all sorts of content - I can imagine not all of it sourced in a responsible way - hence being wary that the output may not be viable for commercial use.

I used to work in advertising so have an interest, now moved on to other things so this is merely for fun.

Another way of doing it is to throw together photos you have taken into a "very messy and clunky composition" then upscale that with a model that will fix all shadows, edges, etc and "just make it look right" based on being trained on "what is looking right" - adding a prompt will make the result even better.

I've done a bunch of that and it's like having a retouch assistant.

Also fun to just give it a poem and see what it makes of it :)

 

[pxl]

..or make strange places and architecture ?

..it's like visiting places simply by describing them :)

 

[pxl]

You can tell I like dystopian abandoned ( ? ) structures :)

 

[Bandersnatch]

Other than the middle one, the structures are clearly not abandoned, as somebody's picking leaves out of the pools and trimming the hedges. Or something is.
Was the prompt 'show me the world a few years hence, when all humans have been made redundant and the AI reigns alone over the depopulated Earth'?

Thanks for sharing the process, btw. The birth(transformation?) of what it means to be an artist is equally fascinating to observe as the advances in the technology themselves.

 

[DaveC426913]

I find myself continually asking how it is doing this?

I mean, I assume when you ask to for a pic of 'a girl in a spacesuit', it looks at common elements of hundreds or thousands of pics that have similar ... tags?
(Anthropomorphized:
"OK I've got 567 images all labelled 'spacesuit', all with these common elements. If I draw a pic that matches those elements, it ought to be a spacesuit." Yes?)

Does it steal stuff, or is it all original? If we look at its input for 'spacesuit', will we find one or a few that are recognizably the inspiration?

 

[pxl]

@Bandersnatch haha this is what I really like about images of "strange places"...inferring their nature from logic like you just did...that immediately builds a story within that location or universe :)

@DaveC426913 here's a video that explains it to some detail...there's a lot more to it but these are the principles...

 

[Algr]

..it's like visiting places simply by describing them :)

That is what the characters in Myst were doing. They would write these books, and it wasn't clear if they were creating worlds or contacting them.

Does it steal stuff, or is it all original?

There are lots of upset artists accusing it of stealing. But if the AI were really doing that, we'd be seeing more examples of people comparing AI output to the "original" images.

 

[SparkBird]

Very kind - thank you !!

I haven't yet trained on photos aside from training a "lora" on my own face just to learn...and from that I realised I need to learn a lot more before I train full models. ( a Lora is a small network trained on a specific subject usually 10 or 15 images that can then be used in combination with a larger model trained on tens of thousands of annotated images ) But you're correct, you could make a Lora using shots of a specific subject like a lighthouse, then remix the look and use of that by combining it with a larger model...that would add a beach and ocean, change the colour and design etc.

I made a few half decent shots of characters that look like me ( easiest way to get a photograph of myself in a suit haha ) but it was overcooked or I did something wrong somewhere and that makes it hard to work with I.E I have a lot more to learn.

There's a strong community that train on all sorts of content - I can imagine not all of it sourced in a responsible way - hence being wary that the output may not be viable for commercial use.

I used to work in advertising so have an interest, now moved on to other things so this is merely for fun.

Another way of doing it is to throw together photos you have taken into a "very messy and clunky composition" then upscale that with a model that will fix all shadows, edges, etc and "just make it look right" based on being trained on "what is looking right" - adding a prompt will make the result even better.

I've done a bunch of that and it's like having a retouch assistant.

Also fun to just give it a poem and see what it makes of it :)

I've seen abt 1 month ago as some guys tested one prompt-poem worked out by different AI tools, generating images and video of the poem text. There were DALL-E, StableDiffusion and 2 another (can't recall names not to find that video). I'd say it was creepy and they did it for a fun. Although, they have shown also retrospective of the same prompt-poem with the same AI tools but made of 3 months before. And that was awful. Than they've shown the same poem with added text-prompts "cleanning out" all the "AI overinvented fragments", setting up parameters of shades, style, creativeness level +destinguishing fragments with added sampling templates etc. The results were really wonderfull. The speed of AI leraning is extreemly high, as you noticed and the level of mastering of AI tools does matter also. I think we're getting to new age of the "art of mastering AI tools". Like it was the art of pencil-drawing, paint-drawing, digital-illustration.... and it's awsome.

 

[Tom.G]

Yet another opportunity for rolling with laughter:
https://news.mit.edu/2023/researchers-chart-captions-ai-vistext-0630

I can just see a chart labeled
"Number Of Dogs Needed To Walk a Spider"

 

[DennisN]

Recently I installed Microsofts Bing app on my Android tablet and it features an AI chat which also has the ability to generate AI images. Very fun, and I was impressed by the results.

Here are some images I just generated (with a Christmas theme)...

Two monkeys as Santa Claus:

And two aliens as Santa Claus:

 

[DennisN]

Another, James Webb Space Telescope with Christmas decorations :

 

[DennisN]

Ok, one more (it's so fun to do it)...
An Earth Christmas bulb:

 

[DennisN]

Recently I installed Microsofts Bing app on my Android tablet and it features an AI chat which also has the ability to generate AI images. Very fun, and I was impressed by the results.

A short guide if anyone wants to try it (it's very easy):On Windows:

For the Bing AI chat, just go to https://www.bing.com/ and click on "Ask Bing Chat".
When I tried it before I couldn't access the chat with Firefox (which is the browser I use),
I had to use the browser Microsoft Edge. But now it seems the AI chat is available via Firefox (and possibly other browsers?).

For AI image generation you need a Microsoft account. I used my old hotmail account which worked fine.
You can generate images in two ways:

1. In the Bing chat, you just type "draw X", where X is the subject of the image, e.g. "a red apple with ears".
2. You can also go to Microsoft Bing Image Creator and generate images there.

On Android:

There are two apps which supports AI chat with image generation, the Microsoft Edge: AI browser app and the Bing app. I prefer the Microsoft Edge app (in landscape mode), since in the Bing app I experienced frequent annoying changes between portrait and landscape mode when generating AI images.

For AI chatting you don't need a Microsoft account, but for AI image generation you need one.

Notes:

Note 1: At the moment you can't access Bing AI with Firefox on Android, you need to use either the Microsoft Edge app or the Bing app.

Note 2: I've tried another Android app for AI chatting, the OpenAI ChatGPT, and it's reasonably small (ca 62 MB) and it seems to work fine. This app does however not support AI image generation.

 

[jack action]

Apparently, there are still some glitches with AI images from text:

Some AI programs are not really vintage car friendly... A simple request for White wall tire with Sombrero hubcap... How hard can that be?

 

[Algr]

Prompt:
cinematic still A giant blimp lifts Godzilla into the stratosphere,
Bright sun, clear black sky, looking up, Godzilla hanging from wires . emotional, harmonious, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy

So I added some extra space at the top and wrote the caption.

 

[Borg]

Well there's something that I can't unsee.

 

[Hornbein]

I found that the novelty of AI art wore off quickly. I got sick of it pretty quickly. There tends to be something grotesque about it.

That being said I still use free AI art generators when I want something that can be slightly creepy and grotesque. They often do as well as a human would. And it's amateur projects that I'd never pay for.

I frequent an artists' group and they feel very threatened by this. Artists don't make much in the first place.

I've seen some pretty impressive AI generated art, but the artist said they had spent hundreds of hours refining it.

I wrote a book and hired artists to do the illustrations. I wanted someone who drew by hand but learned that the artists one finds online almost all draw on computers so I had to give up on that. I tried finding artists though an online site. They showered me with portfolios that were the opposite of what I had requested. It costs them zero to respond so they spam everything. I hired the one artist who had nice sketches in her portfolio but it turned out she hadn't drawn them. She was a fraud! Thank God I hadn't given her any money yet. To heck with all that.

I ended up finding artists on my own in Bali and Paraguay. They depended heavily on computers but nevertheless I was pleased with the results. As the golfers say, it's the Indian not the arrow.

It was before AI art but I'm pretty sure an AI couldn't do the unearthly geometry I needed. Indeed the artists had trouble understanding what I wanted. I learned that descriptions didn't work. I had to draw things myself and have them polish it up. In some cases they refused to deal with it so I ended up using my own drawings.

 

[Tom.G]

Indeed the artists had trouble understanding what I wanted. I learned that descriptions didn't work.

Yup, they assuredly Think differently than most.
But the same can be said about those on this site too.

(Enjoy... and don't let any of the funny people get to you.)

 

[Algr]

I guess I don't fear AI art because I never made money on art in the first place. I do it for fun, and forum games. I get the impression that many people are attracted to art as a career because they think it looks easy: They are taught that all they have to do is "express themselves". Then they try to do practical art for a real paying client and have no idea how to do anything useful. Even Marvel and DC openly say they have no use for art school graduates.

I've seen some pretty impressive AI generated art, but the artist said they had spent hundreds of hours refining it.

Good art is hard. AI hasn't changed a thing. We are in a moment of transition, but learning is fun for me, and I relish the new opportunities.